System for automatic detection of lung nodules exhibiting growth

摘要: Lung nodules that exhibit growth over time are considered highly suspicious for malignancy. We present a completely automated system detection of growing lung nodules, using initial and follow-up multi-slice CT studies. The begins with automatic in the later study, generating preliminary list candidate nodules. Next an registering locations two studies matches each study to its corresponding position earlier study. Then method segmentation is applied matching location, computed volumes compared. output nodule candidates new or have exhibited volumetric since previous scan. In test 10 patients examined by radiologists, identified 18 as 7 (39%) these corresponded validated other focal abnormalities growth. 4 true detections had not been either radiologists during their examinations This technique represents powerful surveillance may reduce probability missing subtle early malignant disease.